waterfall-blueprint

Found your waterfall-blueprint skill while reviewing some project planning tools—the structural approach to breaking down complex deliverables is solid, though I think there's room to tighten up how you're guiding developers through the decision points.

Links:

• GitHub
• Your agentic skill in the SkillzWave marketplace

The TL;DR

You're at 62/100, which puts you in D territory. This is based on Anthropic's skills best practices framework. Your strongest area is Spec Compliance (11/15)—the YAML frontmatter is clean and you've got the naming conventions right. The biggest drag is Utility (10/20) and Progressive Disclosure Architecture (15/30)—there's conceptual value here, but developers need more actionable guidance and concrete templates to actually use this.

What's Working Well

• Clean metadata structure – Your YAML frontmatter is valid and follows conventions, which makes the skill discoverable
• Conceptual framework is sound – The 5-step waterfall breakdown (Goal & Constraints → Design → Implementation → Testing → Versioning) is a logical flow that makes sense for enrichment routing
• Specific domain focus – You're targeting a real problem (provider sequences, throttling, credit policies), not some vague generic task
• grep-friendly formatting – The structure scores points for being easy to parse and navigate

The Big One: Missing Reference Files and Templates

Here's what's holding you back the most: you mention templates in your "Templates" section, but they don't actually exist. You list:

• Waterfall diagram (sequence, inputs, outputs, fallback paths)
• Routing table (provider, criteria, cost, notes)
• Change log with owners + rationale

But none of these are provided. This violates the layered Progressive Disclosure Architecture pattern—detailed content should live in separate reference files, not buried in the main SKILL.md.

The fix: Create a references/ folder with:

• references/waterfall-diagram-template.md – actual example diagram
• references/routing-table-template.md – sample routing table with real columns
• references/changelog-template.md – format example

This alone could add 8 points and solve your PDA problem in one go.

Other Things Worth Fixing

1. Add validation/testing step – Your framework stops at "Versioning," but developers need guidance on validating that the waterfall logic actually works. Add a Step 6 covering test records, fallback path verification, and latency checks against SLA.

2. Trigger phrases are weak – Your description says "Use to design provider sequences" but doesn't include the actual language developers would use like "design enrichment waterfall," "configure provider routing," or "troubleshoot enrichment failures." Add these to the description metadata—it'll help with discoverability.

3. Framework needs procedural steps – Right now it's conceptual. Instead of "Goal & Constraints – define enrichment type, data requirements..." make it concrete: "1. List required data fields (email, phone, title). 2. Set max credits per record (e.g., 5). 3. Define latency SLA (e.g., <2s)."

4. Tighten the Tips section – "Pair with provider-scorecard to continuously optimize routing" is a bit hand-wavy. Be specific: "Run provider-scorecard weekly; adjust routing if success rates change >5%."

Quick Wins

• Create references/ folder with 3 actual templates → +8 points, fixes PDA
• Add Step 6: Testing to the framework → +4 points, fixes Utility gap
• Rewrite description with trigger phrases → +2 points, improves discoverability
• Convert framework to numbered procedures with concrete examples → +3 points, way more actionable

Focus on the templates first—that's where the bang for your buck is.

Checkout your skill here: SkillzWave.ai | SpillWave We have an agentic skill installer that install skills in 14+ coding agent platforms. Check out this guide on how to improve your agentic skills.